MétaCan
Menu
Back to cohort
Record W4293863352 · doi:10.1109/siu55565.2022.9864730

Using Word Embeddings in Detection of Temporal Expressions in Turkish Texts

2022· article· en· W4293863352 on OpenAlex
Ensar Emirali, M. Elif Karslıgil

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venue2022 30th Signal Processing and Communications Applications Conference (SIU) · 2022
Typearticle
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsStantec (Canada)
Fundersnot available
KeywordsTurkishScope (computer science)Computer scienceWord (group theory)Artificial intelligenceNatural language processingSet (abstract data type)The InternetField (mathematics)Speech recognitionLinguisticsMathematicsWorld Wide Web

Abstract

fetched live from OpenAlex

Developing systems for automatically detection of date, time, duration and set expressions containing time information in texts is within the scope of Natural Language Processing research field. When studies for Turkish in the literature are reviewed, it is observed that only date and time expressions are included in the expressions detected by the models developed within the scope of Named Entity Recognition. There are studies to develop only rule-based systems on the subject of detection of temporal expressions in Turkish. Within the scope of this study, first Artificial Neural Networks based model for the detection of temporal expressions in Turkish texts is developed. The input of the developed model is word embeddings. In this study, the developed model success with using word embeddings built by different methods is measured on a dataset consisting of Turkish complaint texts collected from internet websites. By comparing the success of word embeddings on the detection of temporal expressions with the coverage percentages of word embeddings on the dataset, it is concluded that there is no correlation between them.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.847
Threshold uncertainty score0.801

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.002
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0020.002
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.037
GPT teacher head0.315
Teacher spread0.278 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it